AJAR: An Argumentation-based Judging Agents Framework for Ethical Reinforcement Learning
Résumé
An increasing number of socio-technical systems embedding Artificial Intelligence (AI) technologies are deployed, and questions arise about the possible impact of such systems onto humans. We propose a hybrid multi-agent Reinforcement Learning framework consists of learning agents that learn a task-oriented behaviour defined by a set of symbolic moral judging agents to ensure they respect moral values. This framework is applied on the problem of responsible energy distribution for smart grids.
| Origine | Fichiers produits par l'(les) auteur(s) |
|---|---|
| Licence |
![]()
Cite 10.5281/zenodo.7628903 Ouvrage Alcaraz, B., Boissier, O., Chaput, R., & Leturc, C. (2023). AJAR: An Argumentation-based Judging Agents Framework for Ethical Reinforcement Learning (Version v1). Zenodo. https://doi.org/10.5281/ZENODO.7628903